In large-scale problems, standard reinforcement learning algorithms suffer from slow learning speed. In this paper, we follow the framework of using subspaces to tackle this problem. We propose a free-energy minimization framework for selecting the subspaces and integrate the policy of the state-space into the subspaces. Our proposed free-energy minimization framework rests upon Thompson sampling policy and behavioral policy of subspaces and the state-space. It is therefore applicable to a variety of tasks, discrete or continuous state space, model-free and model-based tasks. Through a set of experiments, we show that this general framework highly improves the learning speed. We also provide a convergence proof.
Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences（中国科学院大学）；Great Bay University（Great Bay大学）；Duke-NUS Medical School, National University of Singapore（新加坡国立大学杜克-奈素医学院）
Facebook AI Research（脸书人工智能研究院）；CNRS-ISIR（法国国家科学研究中心-智能系统与机器人研究所）；Sorbonne University（索邦大学）；Ubisoft（育碧）
Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In th…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Hertie Institute for Clinical Brain Research（赫蒂临床脑研究所）；Institute for Computer Engineering, University of Heidelberg（海德堡大学计算机工程学院）
In this paper, we formulate the challenge of re-conceptualising the language game experimental paradigm in the framework of multi-agent reinforcement learning (MARL). If successful, future language game experiments will benefit from the rapid and promising methodological advances in the MARL community, while future MARL experiments on learning emergent communication will benefit from the insights and results gained from language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can eme…
NTT Communication Science Laboratories（NTT通信科学实验室）；Institute of Mathematics for Industry, Kyushu University（九州大学数学工学研究所）；Center for Advanced Intelligence Project, RIKEN（理化学研究所高级智能项目中心）
We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues. The policy network consists of a neural network to find a Koopman invariant subspace, and a pole placement module to adjust the eigenvalues of the Koopman operator. Since the policy network is differentiable, we can train it in an end-to-end fashion using reinforcement learni…
Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient …
Huawei Technologies Israel Research Center（华为技术以色列研究中心）
Subspace optimization methods have the attractive property of reducing large-scale optimization problems to a sequence of low-dimensional subspace optimization problems. However, existing subspace optimization frameworks adopt a fixed update policy of the subspace and therefore appear to be sub-optimal. In this paper, we propose a new \emph{Meta Subspace Optimization} (MSO) framework for large-scale optimization problems, which allows to determine the subspace matrix at each optimization iteration. In order to remain invariant to the optimization problem's dimension, we design an \emph{efficie…
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hidden triggers. During deployment, the adversary can modify observed states in a particular way to trigger unexpected actions and harm the agent. We assume the agent does not have the resources to re-train a good policy. Instead, our defense mechanism sanitizes the backdoor policy by projecting observed states to a 'safe subspace', estimated from a …
We study the sample complexity of teaching, termed as "teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinf…
Key Laboratory of Machine Perception, MOE（教育部机器感知重点实验室）；School of EECS, Peking University（北京大学电子工程与计算机科学学院）；Amazon（亚马逊公司）；Center for Data Science, Peking University（北京大学数据科学中心）
Reinforcement learning (RL) in episodic, factored Markov decision processes (FMDPs) is studied. We propose an algorithm called FMDP-BF, which leverages the factorization structure of FMDP. The regret of FMDP-BF is shown to be exponentially smaller than that of optimal algorithms designed for non-factored MDPs, and improves on the best previous result for FMDPs~\citep{osband2014near} by a factored of $\sqrt{H|\mathcal{S}_i|}$, where $|\mathcal{S}_i|$ is the cardinality of the factored state subspace and $H$ is the planning horizon. To show the optimality of our bounds, we also provide a lower b…
University of California Berkeley（加州大学伯克利分校）；Horizon Robotics（地平线机器人）
The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing. In this work, we introduce a parameter-compositional approach (PaCo) as an attempt to address these challenges. In this framework, a policy subsp…
In this paper, we model nested polar code construction as a Markov decision process (MDP), and tackle it with advanced reinforcement learning (RL) techniques. First, an MDP environment with state, action, and reward is defined in the context of polar coding. Specifically, a state represents the construction of an $(N,K)$ polar code, an action specifies its reduction to an $(N,K-1)$ subcode, and reward is the decoding performance. A neural network architecture consisting of both policy and value networks is proposed to generate actions based on the observed states, aiming at maximizing the over…
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
Federation University Australia（澳大利亚联邦大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；University of Galway（高威大学）；Deakin University（迪肯大学）；Linköping University（林雪平大学）；Universidade do Vale do Rio dos Sinos（南里约 dos Sinos大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）
This paper aims to develop a paradigm that models the learning behavior of intelligent agents (including but not limited to autonomous vehicles, connected and automated vehicles, or human-driven vehicles with intelligent navigation systems where human drivers follow the navigation instructions completely) with a utility-optimizing goal and the system's equilibrating processes in a routing game among atomic selfish agents. Such a paradigm can assist policymakers in devising optimal operational and planning countermeasures under both normal and abnormal circumstances. To this end, we develop a M…
Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
Department of Electrical and Computer Engineering, Duke University, Durham, US（电子工程系，杜克大学，达勒姆，美国）；Department of Computer Science, Duke University, Durham, US（计算机科学系，杜克大学，达勒姆，美国）；Department of Biostatistics and Bioinformatics, Duke University, Durham, US（生物统计学与生物信息学系，杜克大学，达勒姆，美国）；Department of Statistics and Data Science, Yale University, New Haven, US（统计学与数据科学系，耶鲁大学，纽 Haven，美国）
Recent advances in Reinforcement Learning, grounded on combining classical theoretical results with Deep Learning paradigm, led to breakthroughs in many artificial intelligence tasks and gave birth to Deep Reinforcement Learning (DRL) as a field of research. In this work latest DRL algorithms are reviewed with a focus on their theoretical justification, practical limitations and observed empirical properties.
University of Waterloo（滑铁卢大学）；Department of Electrical and Computer Engineering, University of Waterloo, Canada（滑铁卢大学电气与计算机工程系）
A lifelong reinforcement learning system is a learning system that has the ability to learn through trail-and-error interaction with the environment over its lifetime. In this paper, I give some arguments to show that the traditional reinforcement learning paradigm fails to model this type of learning system. Some insights into lifelong reinforcement learning are provided, along with a simplistic prototype lifelong reinforcement learning system.
Department of Informatics Knowledge Technology Institute（信息学知识技术研究所）
Hierarchical abstraction and curiosity-driven exploration are two common paradigms in current reinforcement learning approaches to break down difficult problems into a sequence of simpler ones and to overcome reward sparsity. However, there is a lack of approaches that combine these paradigms, and it is currently unknown whether curiosity also helps to perform the hierarchical abstraction. As a novelty and scientific contribution, we tackle this issue and develop a method that combines hierarchical reinforcement learning with curiosity. Herein, we extend a contemporary hierarchical actor-criti…
The increasing penetration of renewable generations, along with the deregulation and marketization of power industry, promotes the transformation of power market operation paradigms. The optimal bidding strategy and dispatching methodology under these new paradigms are prioritized concerns for both market participants and power system operators, with obstacles of uncertain characteristics, computational efficiency, as well as requirements of hyperopic decision-making. To tackle these problems, the Reinforcement Learning (RL), as an emerging machine learning technique with advantages compared w…
Institute of Digital Games, University of Malta（马耳他大学数字游戏研究所）
This paper introduces a paradigm shift by viewing the task of affect modeling as a reinforcement learning (RL) process. According to the proposed paradigm, RL agents learn a policy (i.e. affective interaction) by attempting to maximize a set of rewards (i.e. behavioral and affective patterns) via their experience with their environment (i.e. context). Our hypothesis is that RL is an effective paradigm for interweaving affect elicitation and manifestation with behavioral and affective demonstrations. Importantly, our second hypothesis-building on Damasio's somatic marker hypothesis-is that emot…
Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests itself in the form of human-level performance on games like \textit{Go}. While RL is emerging as a practical component in real-life systems, most successes have been in Single Agent domains. This report will instead specifically focus on challenges that are unique to Multi-Agent Systems interacting in mixed cooperative and competitive environments. The repor…
University of Sussex（萨塞克斯大学）；Naver Labs Europe（Naver欧洲实验室）
The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the pre-trained distribution towards preferred outputs, in others it is to steer it towards a different distribution over the sample space. Two main paradigms have emerged to tackle this challenge: Reward Maximization (RM) and, more recently, Distribution Matching (DM). RM applies standard Reinforcement Learning (RL) techniques, such as Policy Gradients, to gradually inc…
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
HKUST (GZ)（香港科技大学（广州））；INFORMED-AI Hub（INFORMED-AI中心）；University of Bristol（布里斯托大学）；ELLIS Institute Finland（芬兰ELLIS研究所）；Centre for Artificial Intelligence（人工智能中心）；University College London（伦敦大学学院）；School of Engineering Mathematics and Technology（工程数学与技术学院）
The Technion - Israel Institute of Technology（以色列理工学院）；National University of Singapore（新加坡国立大学）
We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimensionality", MDPs that model real-life problems are typically prohibitively large for such approaches. In this work we employ a reinforcement learning approach to tackle this planning problem: we develop a robust approximate dynamic programming method based on a projected fixed po…
School of ECE, College of Engineering, University of Tehran（德黑兰大学工程学院电气与计算机工程系）
Due to the lack of enough generalization in the state-space, common methods in Reinforcement Learning (RL) suffer from slow learning speed especially in the early learning trials. This paper introduces a model-based method in discrete state-spaces for increasing learning speed in terms of required experience (but not required computational time) by exploiting generalization in the experiences of the subspaces. A subspace is formed by choosing a subset of features in the original state representation (full-space). Generalization and faster learning in a subspace are due to many-to-one mapping o…
Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
TU Darmstadt（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (Hessian.ai)（黑森人工智能中心）；Center for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）；German Research Center for AI (DFKI)（德国人工智能研究中心）；University of Würzburg（维尔茨堡大学）
The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；University of Verona（维罗纳大学）；The Weizmann Institute of Science（魏茨曼科学研究所）
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware can be involved. In this context, it is crucial to optimize the performance of DRL-based agents while providing guarantees about their behavior. This paper presents a novel technique for incorporating domain-expert knowledge into a constrained DRL training loop. Our technique exploits the scenario-based programming paradigm, which is designed to allow specify…
Université de Lille（里尔大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Deepmind（深度思维）；Google Research（谷歌研究院）
Speaker recognition is a well known and studied task in the speech processing domain. It has many applications, either for security or speaker adaptation of personal devices. In this paper, we present a new paradigm for automatic speaker recognition that we call Interactive Speaker Recognition (ISR). In this paradigm, the recognition system aims to incrementally build a representation of the speakers by requesting personalized utterances to be spoken in contrast to the standard text-dependent or text-independent schemes. To do so, we cast the speaker recognition task into a sequential decision…
Recently, many reinforcement learning techniques were shown to have provable guarantees in the simple case of linear dynamics, especially in problems like linear quadratic regulators. However, in practice, many reinforcement learning problems try to learn a policy directly from rich, high dimensional representations such as images. Even if there is an underlying dynamics that is linear in the correct latent representations (such as position and velocity), the rich representation is likely to be nonlinear and can contain irrelevant features. In this work we study a model where there is a hidden…
University of California, Los Angeles（加州大学洛杉矶分校）；Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）
Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We study episodic Markov decision processes with rich observations generated from a small number of latent states. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a no-regret tabular RL algorithm. Theoretically, we prove that as long as the unsupervised learning algorithm enjoys a polynomial sa…
This position paper proposes a fresh look at Reinforcement Learning (RL) from the perspective of data-efficiency. Data-efficient RL has gone through three major stages: pure on-line RL where every data-point is considered only once, RL with a replay buffer where additional learning is done on a portion of the experience, and finally transition memory based RL, where, conceptually, all transitions are stored and re-used in every update step. While inferring knowledge from all explicitly stored experience has lead to a tremendous gain in data-efficiency, the question of how this data is collecte…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Cambricon Technologies（寒武纪科技）；Southern University of Science and Technology（南方科技大学）；Institute of Software, CAS（中国科学院软件研究所）；University of Science and Technology of China（中国科学技术大学）
Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically discover high-quality hierarchical structures is still a great challenge. Previous HRL methods can hardly discover the hierarchical structures in complex environments due to the low exploration efficiency by exploiting the randomness-driven exploration paradigm. To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning fram…
Royal Holloway, University of London（伦敦大学皇家霍洛威学院）；Technische Universität Darmstadt（达姆施塔特工业大学）
Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for summarisation learns a cross-input policy, which requires considerable time, data and parameter tuning due to the huge search spaces and the delayed rewards. Learning input-specific RL policies is a more efficient alternative but so far depends on handcrafted rewards, which are difficult to design and yield poor performance. We propose RELIS, a novel RL paradigm that learns a reward function with Learning-to-Rank (L2R) …
Department of Mathematics, Linn us University, 351 95 Växjö, Sweden
It is well known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper, we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm. Specifically, we propose an extension to categorical reinforcement learning, where distributional learning targets are implicitly based on the total information gathered by an ensemble. We empirically show that this may lead to much more robust initial learning, a stronger individual performance level, and good efficiency on a per-sample basis.
University of Cambridge（剑桥大学）；rlcore；Helmut Schmidt University（赫尔穆特·施密特大学）
Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this end, we introduce RLgraph, a library for designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms. The resulting implementations are robust, incrementally testable, and yield high performance across different deep learning frameworks an…
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Shanghai Qi Zhi Institute（上海期智研究院）；UC Berkeley（加州大学伯克利分校）；UCSD（加州大学圣迭戈分校）
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction and self-imitation. Task reduction tackles a hard-to-solve task by actively reducing it to an easier task whose solution is known by the RL agent. Once the original hard task is successfully solved by task reduction, the agent naturally obtains a self-generated solution trajectory to imitate. By continuously collecting and imitating such demonstrations, the agent is able to progressively expand the solved subspace in…
In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are triggers native to the data distributions the model will be trained on and deployed in. We outline a simple procedure for embedding these, and other, triggers in deep reinforcement learning agents following a multi-task learning paradigm, and demonstrate in three common reinforcement learning environments. We believe that this work has important implications for the security of deep learning models.
The reinforcement learning (RL) problem is rife with sources of non-stationarity, making it a notoriously difficult problem domain for the application of neural networks. We identify a mechanism by which non-stationary prediction targets can prevent learning progress in deep RL agents: \textit{capacity loss}, whereby networks trained on a sequence of target values lose their ability to quickly update their predictions over time. We demonstrate that capacity loss occurs in a range of RL agents and environments, and is particularly damaging to performance in sparse-reward tasks. We then present …
